INDEX

Explanations

specifically bicycles

oai_token-act-pair · gpt-3.5-turbo

references to bicycles and related terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arial

-1.12

arios

-1.01

nyder

-0.99

uminati

-0.83

mberg

-0.81

isite

-0.80

ouri

-0.79

oys

-0.77

orage

-0.77

arity

-0.76

POSITIVE LOGITS

 Friendly

0.83

erg

0.83

puter

0.78

 bicycle

0.77

cling

0.73

 accidents

0.70

 bicycles

0.67

 cafes

0.67

 Bicycle

0.65

 bicycl

0.65

Activations Density 0.008%

specifically bicycles

references to bicycles and related terminology

No Comments

No Known Activations